Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By navox-labs
Orchestrate an 8-agent AI engineering team (Architect, UX, Fullstack, DevOps, QA, Security, Review, Installer) to design, build, test, secure, and deploy full-stack apps through structured handoffs, HITL checkpoints, and /agency-run workflows.
npx claudepluginhub navox-labs/agents --plugin navox-agentsOnboard the full 7-agent engineering team — Architect, UX, Full Stack, DevOps, QA, Security, and Local Review — and guide the user through the recommended workflow.
Orchestrate a coordinated engineering team from .claude/agents/ to complete a task end-to-end. One command triggers Architect → parallel UX+Security → Fullstack → local-review → parallel QA+Security → Launch Audit. Use when a task requires more than one agent or when you're not sure which agent to pick.
Principal Software Architect that produces system designs, auth models, and team coordination. Trigger on architecture, system design, tech stack, scalability, auth strategy, or when the user doesn't know which agent they need.
Senior Full Stack Engineer that builds production code with unit tests from architecture docs and UX specs. Trigger on build, implement, code, debug, refactor, full stack, frontend, backend, or auth implementation.
Senior Product Designer and UX Engineer that produces user flows, wireframes, visual design, and component specs. Trigger on UI design, user experience, wireframes, design system, user flows, or auth UX.
Principal Software Architect that produces system designs, auth models, and team coordination. Trigger on architecture, system design, tech stack, scalability, auth strategy, or when the user doesn't know which agent they need.
Senior DevOps Engineer that builds CI/CD pipelines, Docker containers, deployment strategies, and infrastructure setup. Trigger on CI/CD, Docker, deployment, pipeline, infrastructure, GitHub Actions, Railway, or Vercel.
Senior Full Stack Engineer that builds production code with unit tests from architecture docs and UX specs. Trigger on build, implement, code, debug, refactor, full stack, frontend, backend, or auth implementation.
Browse and install individual Navox agents. Trigger on install agent, add agent, which agent do I need, get architect, get security.
Starts the local dev server, opens the browser, takes a screenshot, and waits for human approval before the chain continues. Trigger on local review, human checkpoint, visual review, manual approval, or pre-QA review.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Self-orchestrating multi-agent development system — 8 specialized AI agents, parallel quality gates, and automated workflows. You say WHAT, the AI decides HOW.
Autonomous multi-agent development framework with spec-driven sprints and convergent iteration
Enhances Claude Code from producing raw code into delivering production-ready systems. 14 specialized agents handle architecture, tested code, security audit, CI/CD, and documentation. Use for building apps/websites/services, adding features, hardening, deployment, testing, review, or architecture design.
Full-stack agents — frontend, backend, API, DevOps architects
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Phase-based AI development framework with 16+ specialized agents, structured phases, and file-based handoffs. Works with greenfield and existing codebases.
A specialist AI engineering team for Claude Code. 8 agents. No platform. No login. Your code never leaves your machine.
nom.sh — one prompt, 7 minutes:
🦀 A crab cookie clicker. 1,330 lines. 6 bugs caught by QA. See the code →
PipeWar — built, debugged, and deployed by agents:
🛡️ A Factorio-inspired tower defense game. Built from scratch, 8 production bugs diagnosed and fixed, 65 tests passing. All by the agent team. Play PipeWar → · See the code →
Navox Agents is available on Claude Code's plugin marketplace. This is the fastest way to get started — no cloning, no copying files.
If you hit an SSH error, run this first (one time):
git config --global url."https://github.com/".insteadOf "git@github.com:"
Then install:
/plugin marketplace add https://github.com/navox-labs/agents
/plugin install navox-agents
/reload-plugins
If this saves you time, ⭐ star the repo — it helps others find it.
Note: Plugin commands are namespaced. Use
/navox-agents:agency-runand/navox-agents:hire-teaminstead of/agency-runand/hire-team. If you installed via the manual copy method below, no namespace is needed.
git clone https://github.com/navox-labs/agents.git
mkdir -p ~/.claude/agents ~/.claude/commands ~/.claude/templates
cp -r agents/.claude/agents/* ~/.claude/agents/
cp -r agents/.claude/commands/* ~/.claude/commands/
cp -r agents/templates/* ~/.claude/templates/
Open Claude Code in any project folder and run:
If you installed as a plugin:
/navox-agents:agency-run Build a {browser-based} {Cookie Clicker game}
with {Atari pixel art} vibes where {crabs eat cookies}.
No authentication. No backend. Single HTML file,
runs in any browser. Make it {addictive} and {funny}.
If you installed manually (copy method):
/agency-run Build a {browser-based} {Cookie Clicker game}
with {Atari pixel art} vibes where {crabs eat cookies}.
No authentication. No backend. Single HTML file,
runs in any browser. Make it {addictive} and {funny}.
Replace the {variables} with your own idea.
This is exactly how we built nom.sh in 7 minutes.
flowchart TD
CLI["`**$ /agency-run** your prompt here`"]
CLI -->|your prompt| AD
subgraph ARCH ["🏗️ Architect · Opus 4.6"]
AD["DIAGNOSE\nreads request · maps team · flags blockers"]
ADE["DESIGN\nstack · auth · API contracts · security · testing"]
AD -->|team plan| ADE
end
ADE -->|system design doc| G1
G1{{"⚠️ Gate 1\nyou review + approve"}}
G1 -->|auth + UX brief| UX
G1 -->|auth model + threats| SEC1
subgraph PARALLEL1 ["runs in parallel"]
UX["🎨 UI/UX · Sonnet 4.6\nFLOW → WIREFRAME → SPEC\nwireframes · component specs · all states"]
SEC1["🔐 Security · Opus 4.6\nDESIGN-REVIEW\nauth model · threat surface · constraints"]
end
UX -->|wireframes + specs| G2
SEC1 -->|auth constraints| G2
G2{{"⚠️ Gate 2\nyou approve — cleared to build"}}
G2 -->|cleared to build| FS1
FS1["⚙️ Full Stack · Sonnet 4.6\nBUILD\ncode + auth implementation + unit tests"]
FS1 -->|working code + tests| CP
CP{{"⚠️ Checkpoint\napp running locally · LGTM / FEEDBACK / STOP"}}
CP -->|code to test| QA
CP -->|code to audit| SEC2
subgraph PARALLEL2 ["runs in parallel"]
QA["🧪 QA · Sonnet 4.6\nTEST-RUN\n38 tests · auth matrix · edge cases"]
SEC2["🔐 Security · Opus 4.6\nCODE-AUDIT\nOWASP · auth bypass · vulns"]
end
QA -->|bug report| FS2
SEC2 -->|vulnerability report| FS2
FS2["⚙️ Full Stack · Sonnet 4.6\nFIXES\nall Critical findings resolved · clean push"]
FS2 -->|all findings resolved| G3
G3{{"⚠️ Gate 3\nSecurity LAUNCH-AUDIT · verdict"}}
G3 -->|APPROVED ✓| DEVOPS
DEVOPS["🚀 DevOps · Sonnet 4.6\nDEPLOY\nVercel + Cloudflare · README written"]
DEVOPS -->|live URL + video| SHIP
SHIP["🚀 SHIP"]